AI agents call ms_chat to retrieve information from M365 MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves Teams chat data for the authenticated user without modifying, executing operations, or causing irreversible changes. While the description is terse, the explicit 'read' verb and server's read-only access model clearly indicate a query operation. Severity is low because chat access is informational only, though exposure could leak sensitive communications.
From the tool's definition Tool description explicitly states 'Read the user' and server description specifies 'read-only access' to Teams chats. The verb 'read' and read-only designation confirm data retrieval with no side effects.
Attacks that exploit this kind of access
Read the user. It is categorised as a Read tool in the M365 MCP MCP Server, which means it retrieves data without modifying state.
Register the M365 MCP server in PolicyLayer and add a rule for ms_chat: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches M365 MCP. Nothing to install.
ms_chat is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the ms_chat rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for ms_chat. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
ms_chat is provided by the M365 MCP server (stumason/m365-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →